About
Computer Science background, ML/AI engineering focus, and a product-minded way of building.
I’m a Computer Science student and ML/AI engineer who likes building intelligent systems that actually ship — from model-serving APIs and ML pipelines to the product surfaces people interact with.
My work sits at the intersection of applied AI, machine-learning systems, and backend engineering: translating research into production services, designing APIs that decouple model execution from application logic, and putting deterministic safety and routing logic around probabilistic components.
I care as much about the product as the model. Good engineering, to me, means framing the right problem, building for reliability, and delivering in small, verifiable slices — so the system stays usable and trustworthy as it grows.
How I build
Problem framing first
Understand the real need and its constraints before reaching for a model or an abstraction.
Safe, reliable by default
Wrap probabilistic systems in deterministic guardrails so behavior degrades gracefully, not dangerously.
Product-minded engineering
Build for the people who actually use the system, not just for the benchmark.
Vertical-slice delivery
Ship small, complete, working increments and iterate from real feedback.